arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1704.02809cs.CV
收藏

基于R-聚类的自我中心视频分割

R-Clustering for Egocentric Video Segmentation

Universitat de Barcelona(巴塞罗那大学);University of Groningen(格罗宁根大学);Computer Vision Center(计算机视觉中心)

Estefania Talavera, Mariella Dimiccoli, Marc Bolaños, Maedeh Aghaei, Petia Radeva

摘要:

在本文中,我们提出了一种新的方法,自我为中心的视频时间分割的基础上整合的统计均值变化检测器和凝聚聚类(AC)内的能量最小化框架。鉴于大多数AC方法的趋势,过度分割视频序列时,聚类他们的帧,我们结合了聚类的概念漂移检测技术(ADWIN),具有严格的性能保证。ADWIN作为基于聚类的视频分割的统计上界。我们将这两种技术集成在一个能量最小化框架中,该框架用于消除这两种技术的决策的歧义,并考虑到视频帧描述符的时间连续性来完成分割。我们目前的实验超过13.000个图像采集与不同的可穿戴相机的自我中心集,表明我们的方法优于国家的最先进的聚类方法。

英文摘要:

In this paper, we present a new method for egocentric video temporal segmentation based on integrating a statistical mean change detector and agglomerative clustering(AC) within an energy-minimization framework. Given the tendency of most AC methods to oversegment video sequences when clustering their frames, we combine the clustering with a concept drift detection technique (ADWIN) that has rigorous guarantee of performances. ADWIN serves as a statistical upper bound for the clustering-based video segmentation. We integrate both techniques in an energy-minimization framework that serves to disambiguate the decision of both techniques and to complete the segmentation taking into account the temporal continuity of video frames descriptors. We present experiments over egocentric sets of more than 13.000 images acquired with different wearable cameras, showing that our method outperforms state-of-the-art clustering methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑